© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75826
    Prev
    Next
    INDEX
    Explanations

    state, State, STATE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    也得
    -1.16
     appeler
    -1.15
     extrêmement
    -1.13
    却没有
    -1.05
     силы
    -1.05
     "
    -1.03
    Prima
    -1.00
     zakresie
    -0.99
     expliquer
    -0.97
     extrême
    -0.96
    POSITIVE LOGITS
     getState
    1.61
     selanjutnya
    1.27
    gy
    1.22
     newState
    1.20
     剤
    1.16
     state
    1.16
     quo
    1.11
    getState
    1.07
     createState
    1.07
     Quo
    1.06
    Activations Density 0.077%

    No Known Activations